© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22513
    Prev
    Next
    INDEX
    Explanations

    combine, merge, split, or save

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uwen
    -0.07
    çī¹å®ļçļĦ
    -0.07
    çī¹å®ļ
    -0.06
    èĩªæĪijä¿ĿæĬ¤
    -0.06
    _CURRENT
    -0.06
    èĩªè¡Į
    -0.06
    ä½łæĿ¥
    -0.06
     caz
    -0.06
     stead
    -0.06
    æľīè¿ij
    -0.06
    POSITIVE LOGITS
    Concat
    0.08
    tring
    0.08
    perk
    0.08
    }:{
    0.08
    bnb
    0.07
    تÙĨ
    0.07
    åľ°æĬĬ
    0.07
    pees
    0.07
    sprintf
    0.07
    efs
    0.07
    Activations Density 0.001%

    No Known Activations